Expose fast_math mode for GEMM through BFloat16

Resolves: COMPMID-4641

Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I7ccc663b2692d40c370794caa906b5be8fd25a32
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5977
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 37 insertions, 32 deletions

diff --git a/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h b/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h
index 2ebb80bef2..fe866dd941 100644
--- a/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h
+++ b/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h
@@ -76,46 +76,51 @@ public:
      * |QASYMM8_SIGNED |QASYMM8_SIGNED     |S32      |QASYMM8_SIGNED |
      * |QASYMM8_SIGNED |QSYMM8_PER_CHANNEL |S32      |QASYMM8_SIGNED |
      *
-     * @param[in]  input        Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
-     *                          while every optional dimension from 4 and above represent a batch of inputs.
-     *                          Data types supported: QASYMM8/QASYMM8_SIGNED/BFLOAT16/F16/F32.
-     * @param[in]  weights      Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
-     *                          Data type supported: QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL/BFLOAT16/F16/F32.
-     * @param[in]  biases       Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
-     *                          Data type supported: Should match @p input data type, except for input of QASYMM8/QASYMM8_SIGNED type where biases should be of S32 type.
-     * @param[out] output       Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
-     *                          Data types supported: Same as @p input.
-     * @param[in]  conv_info    Contains padding and stride information described in @ref PadStrideInfo.
-     * @param[in]  weights_info Specifies if the weights tensor has been reshaped with NEWeightsReshapeKernel. If this is not part of the fully connected layer the weights
-     *                          tensor has also been transposed with cpu::kernels::CpuGemmTranspose1xWKernel. Data type supported: Same as @p input.
-     * @param[in]  dilation     (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
-     * @param[in]  act_info     (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU supported.
-     * @param[in]  num_groups   (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is not supported
+     * @param[in]  input            Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
+     *                              while every optional dimension from 4 and above represent a batch of inputs.
+     *                              Data types supported: QASYMM8/QASYMM8_SIGNED/BFLOAT16/F16/F32.
+     * @param[in]  weights          Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
+     *                              Data type supported: QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL/BFLOAT16/F16/F32.
+     * @param[in]  biases           Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
+     *                              Data type supported: Should match @p input data type, except for input of QASYMM8/QASYMM8_SIGNED type where biases should be of S32 type.
+     * @param[out] output           Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
+     *                              Data types supported: Same as @p input.
+     * @param[in]  conv_info        Contains padding and stride information described in @ref PadStrideInfo.
+     * @param[in]  weights_info     Specifies if the weights tensor has been reshaped with NEWeightsReshapeKernel. If this is not part of the fully connected layer the weights
+     *                              tensor has also been transposed with cpu::kernels::CpuGemmTranspose1xWKernel. Data type supported: Same as @p input.
+     * @param[in]  dilation         (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
+     * @param[in]  act_info         (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU supported.
+     * @param[in]  enable_fast_math (Optional) Enable fast math computation. In case this flag were set, the function could dispatch the fastest implementation
+     *                              available which may introduce a drop of accuracy as well. Default is false
+     * @param[in]  num_groups       (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is not supported
      */
     void configure(const ITensor *input, const ITensor *weights, const ITensor *biases, ITensor *output, const PadStrideInfo &conv_info, const WeightsInfo &weights_info = WeightsInfo(),
-                   const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(), unsigned int num_groups = 1);
+                   const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(), bool enable_fast_math = false, unsigned int num_groups = 1);
     /** Static function to check if given info will lead to a valid configuration of @ref NEGEMMConvolutionLayer
      *
-     * @param[in] input        Source tensor info. 3 lower dimensions represent a single input [width, height, IFM],
-     *                         while every optional dimension from 4 and above represent a batch of inputs.
-     *                         Data types supported: QASYMM8/QASYMM8_SIGNED/BFLOAT16/F16/F32.
-     * @param[in] weights      Weights tensor info. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
-     *                         Data type supported: QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL/BFLOAT16/F16/F32.
-     * @param[in] biases       Biases tensor info. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
-     *                         Data type supported: Should match @p input data type, except for input of QASYMM8/QASYMM8_SIGNED type where biases should be of S32 type.
-     * @param[in] output       Destination tensor info. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
-     *                         Data types supported: Same as @p input.
-     * @param[in] conv_info    Contains padding and stride information described in @ref PadStrideInfo.
-     * @param[in] weights_info Specifies if the weights tensor has been reshaped with NEWeightsReshapeKernel. If this is not part of the fully connected layer the weights
-     *                         tensor has also been transposed with cpu::kernels::CpuGemmTranspose1xWKernel. Data type supported: Same as @p input.
-     * @param[in] dilation     (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
-     * @param[in] act_info     (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU supported.
-     * @param[in] num_groups   (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is not supported
+     * @param[in] input            Source tensor info. 3 lower dimensions represent a single input [width, height, IFM],
+     *                             while every optional dimension from 4 and above represent a batch of inputs.
+     *                             Data types supported: QASYMM8/QASYMM8_SIGNED/BFLOAT16/F16/F32.
+     * @param[in] weights          Weights tensor info. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
+     *                             Data type supported: QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL/BFLOAT16/F16/F32.
+     * @param[in] biases           Biases tensor info. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
+     *                             Data type supported: Should match @p input data type, except for input of QASYMM8/QASYMM8_SIGNED type where biases should be of S32 type.
+     * @param[in] output           Destination tensor info. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
+     *                             Data types supported: Same as @p input.
+     * @param[in] conv_info        Contains padding and stride information described in @ref PadStrideInfo.
+     * @param[in] weights_info     Specifies if the weights tensor has been reshaped with NEWeightsReshapeKernel. If this is not part of the fully connected layer the weights
+     *                             tensor has also been transposed with cpu::kernels::CpuGemmTranspose1xWKernel. Data type supported: Same as @p input.
+     * @param[in] dilation         (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
+     * @param[in] act_info         (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU supported.
+     * @param[in] enable_fast_math (Optional) Enable fast math computation. In case this flag were set, the function could dispatch the fastest implementation
+     *                             available which may introduce a drop of accuracy as well. Default is false
+     * @param[in] num_groups       (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is not supported
      *
      * @return a status
      */
     static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const PadStrideInfo &conv_info,
-                           const WeightsInfo &weights_info = WeightsInfo(), const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(), unsigned int num_groups = 1);
+                           const WeightsInfo &weights_info = WeightsInfo(), const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(),
+                           bool enable_fast_math = false, unsigned int num_groups = 1);
 
     // Inherited methods overridden:
     void run() override;